Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,68 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+SmallThinker-4BA0.6B-Instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,119 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+---
+## Introduction
+
+<p align="center">
+       &nbsp&nbsp🤗 <a href="https://huggingface.co/PowerInfer">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/PowerInfer">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://github.com/SJTU-IPADS/SmallThinker/blob/main/smallthinker-technical-report.pdf">Technical Report</a> &nbsp&nbsp 
+</p>
+
+SmallThinker is a family of **on-device native** Mixture-of-Experts (MoE) language models specially designed for local deployment,
+co-developed by the **IPADS and School of AI at Shanghai Jiao Tong University** and **Zenergize AI**.
+Designed from the ground up for resource-constrained environments,
+SmallThinker brings powerful, private, and low-latency AI directly to your personal devices,
+without relying on the cloud.
+
+## Performance
+
+Note: The model is trained mainly on English.
+
+| Model | MMLU | GPQA-diamond | GSM8K | MATH-500 | IFEVAL | LIVEBENCH | HUMANEVAL | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| **SmallThinker-4BA0.6B-Instruct** | **66.11** | **31.31** | 80.02 | <u>60.60</u> | 69.69 | **42.20** | **82.32** | **61.75** |
+| Qwen3-0.6B | 43.31 | 26.77 | 62.85 | 45.6 | 58.41 | 23.1 | 31.71 | 41.67 |
+| Qwen3-1.7B | <u>64.19</u> | <u>27.78</u> | <u>81.88</u> | **63.6** | 69.50 | <u>35.60</u> | 61.59 | <u>57.73</u> |
+| Gemma3nE2b-it | 63.04 | 20.2 | **82.34** | 58.6 | **73.2** | 27.90 | <u>64.63</u> | 55.70 |
+| Llama-3.2-3B-Instruct | 64.15 | 24.24 | 75.51 | 40 | <u>71.16</u> | 15.30 | 55.49 | 49.41 |
+| Llama-3.2-1B-Instruct | 45.66 | 22.73 | 1.67 | 14.4 | 48.06 | 13.50 | 37.20 | 26.17 |
+
+For the MMLU evaluation, we use a 0-shot CoT setting.
+
+All models are evaluated in non-thinking mode.
+
+
+## Speed
+| Model                                         | Memory(GiB)         | i9 14900 | 1+13 8gen4 | rk3588 (16G) | rk3576 | Raspberry PI 5 | RDK X5 | rk3566 |
+|-----------------------------------------------|---------------------|----------|------------|--------------|--------|----------------|--------|--------|
+| SmallThinker 4B+sparse ffn +sparse lm_head    | 2.24                | 108.17   | 78.99      | 39.76        | 15.10  | 28.77          | 7.23   | 6.33   |
+| SmallThinker 4B+sparse ffn +sparse lm_head+limited memory | limit 1G| 29.99    | 20.91      | 15.04        | 2.60   | 0.75           | 0.67   | 0.74   |
+| Qwen3 0.6B                                    | 0.6                 | 148.56   | 94.91      | 45.93        | 15.29  | 27.44          | 13.32  | 9.76   |
+| Qwen3 1.7B                                    | 1.3                 | 62.24    | 41.00      | 20.29        | 6.09   | 11.08          | 6.35   | 4.15   |
+| Qwen3 1.7B+limited memory                     | limit 1G            | 2.66     | 1.09       | 1.00         | 0.47   | -              | -      | 0.11   |
+| Gemma3n E2B                                   | 1G, theoretically   | 36.88    | 27.06      | 12.50        | 3.80   | 6.66           | 3.46   | 2.45   |
+
+Note: i9 14900, 1+13 8ge4 use 4 threads, others use the number of threads that can achieve the maximum speed. All models here have been quantized to q4_0.
+
+You can deploy SmallThinker with offloading support using [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer/tree/main/smallthinker)
+
+## Model Card
+
+<div align="center">
+
+| **Architecture** | Mixture-of-Experts (MoE) |
+|:---:|:---:|
+| **Total Parameters** | 4B |
+| **Activated Parameters** | 0.6B |
+| **Number of Layers** | 32 |
+| **Attention Hidden Dimension** | 1536 |
+| **MoE Hidden Dimension** (per Expert) | 768 |
+| **Number of Attention Heads** | 12 |
+| **Number of Experts** | 32 |
+| **Selected Experts per Token** | 4 |
+| **Vocabulary Size** | 151,936 |
+| **Context Length** | 32K |
+| **Attention Mechanism** | GQA |
+| **Activation Function** | ReGLU |
+</div>
+
+## How to Run
+
+### Transformers
+
+`transformers==4.53.3` is required, we are actively working to support the latest version.
+The following contains a code snippet illustrating how to use the model generate content based on given inputs.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+path = "PowerInfer/SmallThinker-4BA0.6B-Instruct"
+device = "cuda"
+
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)
+
+messages = [
+    {"role": "user", "content": "Give me a short introduction to large language model."},
+]
+model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(device)
+
+model_outputs = model.generate(
+    model_inputs,
+    do_sample=True,
+    max_new_tokens=1024
+)
+
+output_token_ids = [
+    model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs))
+]
+
+responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0]
+print(responses)
+
+```
+
+### ModelScope
+
+`ModelScope` adopts Python API similar to (though not entirely identical to) `Transformers`. For basic usage, simply modify the first line of the above code as follows:
+
+```python
+from modelscope import AutoModelForCausalLM, AutoTokenizer
+```
+## Statement
+- Due to the constraints of its model size and the limitations of its training data, its responses may contain factual inaccuracies, biases, or outdated information.
+- Users bear full responsibility for independently evaluating and verifying the accuracy and appropriateness of all generated content.
+- SmallThinker does not possess genuine comprehension or consciousness and cannot express personal opinions or value judgments.
+

SmallThinker-4BA0.6B-Instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece3698a81dc19e118113b9d16b57b9d97765a97def6ff08b67f82efb16e63b3
+size 8546216928

SmallThinker-4BA0.6B-Instruct-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7083e6363278786120c10f18d5bc7b9f4a2e347fd35cc1214a3431f636c197f6
+size 6044994528

SmallThinker-4BA0.6B-Instruct-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f915d3595fef991440c60c6616590058ffb30f758d5c1ac19b1a6d43d85bdcb
+size 6044994528

SmallThinker-4BA0.6B-Instruct-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df2a9f44764191880546437c355b1c7dc53fec91be9885bbf88fe611ebb3388
+size 16763072

SmallThinker-4BA0.6B-Instruct-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8565d54ae73a16a55d4c7714189fc4f797de3d5e7d0485ad0406f0ff761c192
+size 1692099872

SmallThinker-4BA0.6B-Instruct-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599098043d5b16400c8647db7be07bba0182a9a229617b36b591ceea607cade9
+size 1687946528

SmallThinker-4BA0.6B-Instruct-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c7bb2a1759a9cccac1dc8e4dca378d857be0d6fe5cc4248341700ebec04446
+size 1531581728

SmallThinker-4BA0.6B-Instruct-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b0adfdefbed2a7b111c0e468215cc727f9ecdad2b470446ec7ac9ae7b10913
+size 1809419552

SmallThinker-4BA0.6B-Instruct-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd83727b771dcd73d685ee112d8eb164be39255ea0a01537407abff1beeeb1d
+size 2367598880

SmallThinker-4BA0.6B-Instruct-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfe96400e38c1e9070904188b2c6aaf96c4461f72401efca4213ba3cd9d4146
+size 2303741216

SmallThinker-4BA0.6B-Instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf25605a9dedec7aee4c6248fb76ee2b872663628f15cf295b3792b80f942d3
+size 2412711200

SmallThinker-4BA0.6B-Instruct-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d0486c1b25a2ba123bd1d73cec25580a4e9b9d71f03e11f5d402aa5e3278d9
+size 2679385376

SmallThinker-4BA0.6B-Instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10fe6efa6d7b17f6c6d78d8a692f779b6ceff9068a9a4033a20d033e6235a99
+size 2768236832

SmallThinker-4BA0.6B-Instruct-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f34699249269b4ef5e5d90ac15ffb47dce967df35a0ad7680b453f30554a47
+size 2649043232

SmallThinker-4BA0.6B-Instruct-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3d7ffcb57fff2b0f908882181c73e13227f7cb037a7a5c65f84568b4b15676
+size 2946059552

SmallThinker-4BA0.6B-Instruct-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e6485c028a75ea6c00f379ed8603c0401253e4f3568b7c6ee37fd76be98fdb
+size 3212733728

SmallThinker-4BA0.6B-Instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958193a4829d100292a5268ea33a4fb24ea360a4fcd39421e99ceaf5540d7c3b
+size 3171823904

SmallThinker-4BA0.6B-Instruct-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb17878e2a4b0988bddb4dfa3a1e84016d169f647e09a594de581e4628281951
+size 3131298080

SmallThinker-4BA0.6B-Instruct-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c0bb0f4f769f7869a402321be28c98454e4780f2b85a738108eedb7f020a2e
+size 3512742176

SmallThinker-4BA0.6B-Instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3048b15013197faf05e2e96be753bb661192a1343caee0fc02a6910d621c6d5
+size 4546104288